Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to training and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    training and trained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
    EDEFAULT
    -0.67
    expandindo
    -0.64
     AssemblyCulture
    -0.64
     HttpNotFound
    -0.63
     հղումներ
    -0.62
    出版年
    -0.61
     незавершена
    -0.60
    URIComponent
    -0.60
    VersionUID
    -0.60
    POSITIVE LOGITS
     trained
    0.85
     Trained
    0.83
    trained
    0.78
    Trained
    0.76
     train
    0.68
     Train
    0.64
     TRAIN
    0.60
    train
    0.59
    Train
    0.59
     untrained
    0.54
    Act Density 0.011%

    No Known Activations